Crude oil price forecasting based on internet concern using an extreme learning machine

The growing internet concern (IC) over the crude oil market and related events influences market trading, thus creating further instability within the oil market itself. We propose a modeling framework for analyzing the effects of IC on the oil market and for predicting the price volatility of crude oil’s futures market. This novel approach decomposes the original time series into intrinsic modes at different time scales using bivariate empirical mode decomposition (BEMD). The relationship between the oil price volatility and IC at an individual frequency is investigated. By utilizing decomposed intrinsic modes as specified characteristics, we also construct extreme learning machine (ELM) models with variant forecasting schemes. The experimental results illustrate that ELM models that incorporate intrinsic modes and IC outperform the baseline ELM and other benchmarks at distinct horizons. Having the power to improve the accuracy of baseline models, internet searching is a practical way of quantifying investor attention, which can help to predict short-run price fluctuations in the oil market.     

Trust Promoting Seals in Electronic Markets

Abstract

In order to promote web sales, companies conducting electronic commerce are constantly seeking viable and efficient ways to increase web traffic. One approach is to build consumers' trust, and ultimately to increase web sales. Many business-to-consumer online merchants follow this approach and display trust-promoting seals on their websites. However, whether these seals really fulfill the tasks they have promised has remained unexplored. This study empirically examines the influence of trust-promoting seals on consumers' online purchasing decisions. The results show that the trust-promoting seals are generally effective in promoting web sales, and some seals enhance promotion better than others.     

The information quality and source credibility matter in customers’ evaluation toward food O2O commerce

This study examines customer’s decision making when purchasing food product through O2O commerce applying the elaboration likelihood model (ELM) and the technology acceptance model (TAM). Further, this research investigates which information processing path, central route (information quality) or peripheral route (source credibility), is related to purchase frequency. Results of the data analysis demonstrate (1) the positive relationship between information quality, perceived usefulness, and perceived ease of use; (2) the significant relationship between source credibility, perceived usefulness, and perceived ease of use; (3) the significant influence of perceived usefulness and perceived ease of use on customer trust; and (4) the significant relationships among customer trust, attitudes, and behavioral intentions. In addition, customers with high purchase frequency tend to process messages via the central route, while customers with low purchase frequency focus on the peripheral route. These findings provide theoretical and managerial implications that contribute to O2O commerce marketing.     

Predicting monthly biofuel production using a hybrid ensemble forecasting methodology

This paper proposes a hybrid ensemble forecasting methodology that integrating empirical mode decomposition (EMD), long short-term memory (LSTM) and extreme learning machine (ELM) for the monthly biofuel (a typical agriculture-related energy) production based on the principle of decomposition—reconstruction—ensemble. The proposed methodology involves four main steps: data decomposition via EMD, component reconstruction via a fine-to-coarse (FTC) method, individual prediction via LSTM and ELM algorithms, and ensemble prediction via a simple addition (ADD) method. For illustration and verification, the biofuel monthly production data of the USA is used as the our sample data, and the empirical results indicate that the proposed hybrid ensemble forecasting model statistically outperforms all considered benchmark models considered in terms of the forecasting accuracy. This indicates that the proposed hybrid ensemble forecasting methodology integrating the EMD-LSTM-ELM models based on the decomposition—reconstruction—ensemble principle has been proved to be a competitive model for the prediction of biofuel production.     

Dual-route communication of destination websites

To understand the communication route of destination websites, this study employed the elaboration likelihood model (ELM) which is a dual-route, multi-process model of persuasive message processing. That is, this study proposed a theoretical model for the dual-route persuasive process based on ELM, investigated its antecedents and consequences, and identified the moderating effect of involvement. Structural Equation Modeling (SEM) is used to test the validity of the conceptual model. The results indicate that highly involved people are inclined to elaborate on information (central route), while people with low involvement are likely to make judgments based on simple cues (peripheral route). Website design characteristics are an important antecedent of both central and peripheral-route persuasions. Attitudes resulting from careful consideration via the central route are more predictive of conation and behavior (further information searching and travel intentions) than those formed via the peripheral route. The study provides a foundation for further tourism research investigating the Internet as a persuasive tool, and suggests strategies for website designers.     

广告媒体的变化趋势对ELM理论应用的影响

消费需求在我国的经济增长模式中起着越来越重要的作用。要想有效地刺激消费者的购买欲望,需要强化市场营销策划人员在广告与促销手段上的说服能力。在理论研究中,ELM是比较权威的以心理角度进行说服性分析的理论,而在广告与促销的实际应用中,市场营销管理者需要结合当前广告媒体的变化趋势避免中枢途径和边缘途径使用的一些误区。     

Metaverse mingle: Discovering dating intentions in metaverse

The present work represents a mixed-method investigation to redefine Elaboration Likelihood Model (ELM) using some innovative variables to investigate dating-partner behaviour in the metaverse. In addition, it seeks proof that realistic threat and perceived trust have a moderating role in this proposed model. The research is split into two parts: in the first stage, dating app users' responses have been collected from online reviews posted on social media sites. Python have been used to find out the constructs from the content analysis. Then using the constructs second phase have been started where the model has been validated by confirmatory analysis. Perceived trust moderates the association between perceived attitude and dating intention in Metaverse whereas realistic threat don't have. Our research showed that apart from perceived accuracy of information all the other factors are having significant association towards perceived attitude. Our findings highlight the importance of both channels in persuading consumers to try out metaverse dating. In order to earn the users' trust, they must resolve their concerns over privacy and security in the online world. To achieve this, strict user verification and security procedures should be implemented.     

Investigating the impact of social media images’ value,consumer engagement,and involvement on eWOM of a tourism destination: A transmittal mediation approach

Tourism organizations use social media to promote their destinations and attract new customers. However, there is a challenge in how tourism organizations can choose or create social media images to successfully attract consumers' attention, induce their engagement with the destination, and motivate their eWOM behavior. This study aims to identify and test the direct and indirect factors related to social media images of tourism destinations that could predict eWOM. Using the Stimulus-Organism-Response (S–O-R) as an umbrella framework, we integrated Ducoffe's model and the Elaboration Likelihood Model (ELM), to study the role of social media destination images' features (entertainment, informativeness, irritation, credibility, personalization, and incentives) on consumer's perceived value and eWOM through consumer engagement and involvement. Using a survey research method, we collected data from 307 individuals and tested the proposed structural model using the PLS-SEM-based transmittal mediation approach. The findings supported the proposed relationships providing valuable theoretical and practical implications.     

非结构化文本语言性对公益众筹项目筹资绩效的影响

本文基于扎根理论和精细加工可能性模型(ELM)构建出了影响公益众筹项目筹资绩效的文本语言风格模型.对新浪微公益网站中的16369个项目进行回归分析,研究发现,从外围路径分析,项目标题中直接表达求助者本身的诉求不利于项目的成功;而含有个体标签与积极情感的项目标题能说服潜在捐助者捐赠.从中央路径分析,众筹项目详情只有综合蕴含清晰故事结构、具体细节和情感诉求的特点方能极大提升项目筹款达成率.研究同时发现,项目类型在文本语言风格与项目成功的关系中具有调节作用.本文研究成果有助于项目发起人从非结构化众筹语言本身出发对项目描述进行优化改进,进而有效提高项目筹款达成率.     

Designing Effective Websites: The Moderating Role of User Internet Experience

ABSTRACT

The objective of this study was to analyze the effectiveness of various aspects relating to execution of a Website: Presentation format, quantity and type of content. We developed experimental Websites and we found that in high-involvement context this effectiveness is not influenced as much by the format of presentation of the Website as by the quantity and type of content offered. The extension of the Website content generates more favorable, affective and behavioral responses only when such extension has an informative nature. Moreover, we found evidence of the moderating role of the individual's Web experience in the advertising persuasion process. Therefore, the results of this investigation can provide recommendations to the organizations on how to create effective Websites.